Automated layer-wise solution for ensemble deep randomized feed-forward neural network

<p dir="ltr">The randomized feed-forward neural network is a single hidden layer feed-forward neural network that enables efficient learning by optimizing only the output weights. The ensemble deep learning framework significantly improves the performance of randomized neural network...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Minghui Hu (2457952) (author)
مؤلفون آخرون: Ruobin Gao (16003195) (author), Ponnuthurai N. Suganthan (17347024) (author), M. Tanveer (1758181) (author)
منشور في: 2022
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513539494903808
author Minghui Hu (2457952)
author2 Ruobin Gao (16003195)
Ponnuthurai N. Suganthan (17347024)
M. Tanveer (1758181)
author2_role author
author
author
author_facet Minghui Hu (2457952)
Ruobin Gao (16003195)
Ponnuthurai N. Suganthan (17347024)
M. Tanveer (1758181)
author_role author
dc.creator.none.fl_str_mv Minghui Hu (2457952)
Ruobin Gao (16003195)
Ponnuthurai N. Suganthan (17347024)
M. Tanveer (1758181)
dc.date.none.fl_str_mv 2022-12-01T15:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.neucom.2022.09.148
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Automated_layer-wise_solution_for_ensemble_deep_randomized_feed-forward_neural_network/24516556
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Machine learning
Randomized feed-forward neural network
Random vector functional link
Automated machine learning
Bayesian optimization
Ensemble deep random vector functional link
dc.title.none.fl_str_mv Automated layer-wise solution for ensemble deep randomized feed-forward neural network
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">The randomized feed-forward neural network is a single hidden layer feed-forward neural network that enables efficient learning by optimizing only the output weights. The ensemble deep learning framework significantly improves the performance of randomized neural networks. However, the framework’s capabilities are limited by traditional hyper-parameter selection approaches. Meanwhile, different random network architectures, such as the existence or lack of a direct link and the mapping of direct links, can also strongly affect the results. We present an automated learning pipeline for the ensemble deep randomized feed-forward neural network in this paper, which integrates hyper-parameter selection and randomized network architectural search via Bayesian optimization to ensure robust performance. Experiments on 46 UCI tabular datasets show that our strategy produces state-of-the-art performance on various tabular datasets among a range of randomized networks and feed-forward neural networks. We also conduct ablation studies to investigate the impact of various hyper-parameters and network architectures.</p><h2>Other Information</h2><p dir="ltr">Published in: Neurocomputing<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.neucom.2022.09.148" target="_blank">https://dx.doi.org/10.1016/j.neucom.2022.09.148</a></p>
eu_rights_str_mv openAccess
id Manara2_e5351e55cd4c99e6aec1a33b95b5430c
identifier_str_mv 10.1016/j.neucom.2022.09.148
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24516556
publishDate 2022
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Automated layer-wise solution for ensemble deep randomized feed-forward neural networkMinghui Hu (2457952)Ruobin Gao (16003195)Ponnuthurai N. Suganthan (17347024)M. Tanveer (1758181)Information and computing sciencesArtificial intelligenceMachine learningRandomized feed-forward neural networkRandom vector functional linkAutomated machine learningBayesian optimizationEnsemble deep random vector functional link<p dir="ltr">The randomized feed-forward neural network is a single hidden layer feed-forward neural network that enables efficient learning by optimizing only the output weights. The ensemble deep learning framework significantly improves the performance of randomized neural networks. However, the framework’s capabilities are limited by traditional hyper-parameter selection approaches. Meanwhile, different random network architectures, such as the existence or lack of a direct link and the mapping of direct links, can also strongly affect the results. We present an automated learning pipeline for the ensemble deep randomized feed-forward neural network in this paper, which integrates hyper-parameter selection and randomized network architectural search via Bayesian optimization to ensure robust performance. Experiments on 46 UCI tabular datasets show that our strategy produces state-of-the-art performance on various tabular datasets among a range of randomized networks and feed-forward neural networks. We also conduct ablation studies to investigate the impact of various hyper-parameters and network architectures.</p><h2>Other Information</h2><p dir="ltr">Published in: Neurocomputing<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.neucom.2022.09.148" target="_blank">https://dx.doi.org/10.1016/j.neucom.2022.09.148</a></p>2022-12-01T15:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.neucom.2022.09.148https://figshare.com/articles/journal_contribution/Automated_layer-wise_solution_for_ensemble_deep_randomized_feed-forward_neural_network/24516556CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/245165562022-12-01T15:00:00Z
spellingShingle Automated layer-wise solution for ensemble deep randomized feed-forward neural network
Minghui Hu (2457952)
Information and computing sciences
Artificial intelligence
Machine learning
Randomized feed-forward neural network
Random vector functional link
Automated machine learning
Bayesian optimization
Ensemble deep random vector functional link
status_str publishedVersion
title Automated layer-wise solution for ensemble deep randomized feed-forward neural network
title_full Automated layer-wise solution for ensemble deep randomized feed-forward neural network
title_fullStr Automated layer-wise solution for ensemble deep randomized feed-forward neural network
title_full_unstemmed Automated layer-wise solution for ensemble deep randomized feed-forward neural network
title_short Automated layer-wise solution for ensemble deep randomized feed-forward neural network
title_sort Automated layer-wise solution for ensemble deep randomized feed-forward neural network
topic Information and computing sciences
Artificial intelligence
Machine learning
Randomized feed-forward neural network
Random vector functional link
Automated machine learning
Bayesian optimization
Ensemble deep random vector functional link